AI Assistant (Billy) & Agents

Use Billy to investigate and draft policies, triage with MCP tools, connect (and credential) AI agents to Chainsaw, and check the packages a coding agent installs.

How to Use Billy to Investigate Packages and Draft Policies Ask Billy natural language questions about your package consumption, vulnerabilities, and policy gaps, then review and approve Billy's policy proposals. Beginner 15 minutes All Personas How to Use Billy MCP Tools for Violation Triage Run inventory queries, simulate patches, and route violations to owners — all from a Billy chat. Walks through the four tool calls Billy can make on your behalf and the approval flow that keeps you in control. Intermediate 20 minutes Security Engineers / DevOps How to Connect Claude / Cursor / GPT to Chainsaw via the Built-in MCP Server Wire your AI agent into the Chainsaw control plane with the Model Context Protocol — give the agent inventory queries, patch-simulation, affected-by lookups, and owner routing without writing a custom integration. Intermediate 20 minutes ML Platform Engineers / Security Engineers / Developers How to Issue and Rotate AI-Agent Client Credentials Mint a dedicated AI-agent credential, scope it to the right MCP tools and repos, and rotate the secret on a schedule without breaking the agent's session. Beginner 15 minutes Security Engineers / Platform Engineers How to Check a Coding Agent's Package Installs with the Claude Code Hook Run the Chainsaw install guard on every package install Claude Code is about to run — npm, pip, npx, uvx and the rest — and turn a malicious or typosquatted package into a refusal the agent reads, before anything is fetched. Beginner 5 minutes Developers / Security Engineers

Billy is Chainsaw’s AI assistant — it investigates violations and drafts policies in natural language, grounded in your own data. This section covers both sides of AI in your supply chain: using Billy to investigate, draft policies, and drive triage through MCP tools, then connecting agents (Claude, Cursor, GPT) to Chainsaw over MCP and issuing them scoped, rotatable credentials, and checking every package a coding agent installs with the Claude Code hook.

Billy is fail-closed by identity. Every Billy action runs under a verifiable identity with RBAC-gated tools — it cannot read or change anything the calling identity is not authorized for.

Where to next

For model-artifact security (pickle, prompt injection, MCP provenance), see AI/ML Supply Chain.